Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 797 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.8924. Min Act: -0.1700

Data Index: 23935 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.8612. Min Act: -0.1700

Data Index: 264683 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.8612. Min Act: -0.1700

Data Index: 293749 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.8924. Min Act: -0.1700

Data Index: 104150 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.8924. Min Act: -0.1700

Data Index: 746662 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7673. Min Act: -0.1700

Data Index: 1198283 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7673. Min Act: -0.1700

Data Index: 551143 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7673. Min Act: -0.1700

Data Index: 470751 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7673. Min Act: -0.1700

Data Index: 463102 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7360. Min Act: -0.1700

Data Index: 305135 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7986. Min Act: -0.1700

Data Index: 632621 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7986. Min Act: -0.1700

Data Index: 14825 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7673. Min Act: -0.1700

Data Index: 1042954 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7360. Min Act: -0.1700

Data Index: 1131563 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7047. Min Act: -0.1700

Data Index: 1073370 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7986. Min Act: -0.1700

Data Index: 429681 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7360. Min Act: -0.1700

Data Index: 1532529 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.6734. Min Act: -0.1700

Data Index: 1509455 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.7360. Min Act: -0.1700

Data Index: 612934 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 3.8924. Min Range: -3.8924

Max Act: 3.6734. Min Act: -0.1700

Data Index: 1165464 (C4 (Web Text))

Max Activating Token Index: 474